Toward Robust IoT Device Authentication: Cross-Day Specific Emitter Identification via Domain Adaptation

Specific emitter identification (SEI) exploits device-dependent RF fingerprints to distinguish individual transmitters and is important for securing large-scale Internet-of-Things (IoT) deployments. While deep SEI can achieve near-perfect accuracy under same-day evaluation, real deployments rarely satisfy this assumption. At scale, per-day labeling is infeasible; models must therefore generalize from a labeled source day to an unlabeled target day, where day-to-day propagation drift induces distribution shifts and can substantially degrade performance under direct transfer (without adaptation). To address this challenge, we propose a unified unsupervised domain adaptation (UDA) framework for cross-day SEI that requires neither hardware calibration nor handcrafted features. The proposed objective integrates adversarial domain alignment, confidence-aware pseudo-labeling to exploit high-confidence target samples safely, and a cross-domain contrastive regularizer to preserve class-discriminative geometry. We further provide an analysis offering insight into how each component contributes to target-domain generalization. Experiments on two public RF benchmarks from different wireless technologies demonstrate robust cross-day performance across diverse transfers. On WiSig–ManySig, our method achieves 99.78% mean cross-day accuracy over six source-to-target day transfers, ranking best in five cases and remaining within 0.04% of the best in the remaining case. On a LoRa benchmark, it achieves 90.64% mean cross-day accuracy over ten day-transfer pairs, validating the framework beyond Wi-Fi and under larger transfer diversity.